knitr::opts_chunk$set(
  fig.width = 6,
  fig.asp = .6,
  out.width = "90%"
)

library(tidyverse)
## ── Attaching packages ──────────────────────────────────────────────────────── tidyverse 1.2.1 ──
## ✔ ggplot2 3.0.0     ✔ purrr   0.2.5
## ✔ tibble  1.4.2     ✔ dplyr   0.7.6
## ✔ tidyr   0.8.1     ✔ stringr 1.3.1
## ✔ readr   1.1.1     ✔ forcats 0.3.0
## ── Conflicts ─────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
library(ggridges)
## 
## Attaching package: 'ggridges'
## The following object is masked from 'package:ggplot2':
## 
##     scale_discrete_manual

Data import

library(rnoaa)

weather_df = 
  rnoaa::meteo_pull_monitors(c("USW00094728", "USC00519397", "USS0023B17S"),
                      var = c("PRCP", "TMIN", "TMAX"), 
                      date_min = "2017-01-01",
                      date_max = "2017-12-31") %>%
  mutate(
    name = recode(id, USW00094728 = "CentralPark_NY", 
                      USC00519397 = "Waikiki_HA",
                      USS0023B17S = "Waterhole_WA"),
    tmin = tmin / 10,
    tmax = tmax / 10) %>%
  select(name, id, everything())
weather_df
## # A tibble: 1,095 x 6
##    name           id          date        prcp  tmax  tmin
##    <chr>          <chr>       <date>     <dbl> <dbl> <dbl>
##  1 CentralPark_NY USW00094728 2017-01-01     0   8.9   4.4
##  2 CentralPark_NY USW00094728 2017-01-02    53   5     2.8
##  3 CentralPark_NY USW00094728 2017-01-03   147   6.1   3.9
##  4 CentralPark_NY USW00094728 2017-01-04     0  11.1   1.1
##  5 CentralPark_NY USW00094728 2017-01-05     0   1.1  -2.7
##  6 CentralPark_NY USW00094728 2017-01-06    13   0.6  -3.8
##  7 CentralPark_NY USW00094728 2017-01-07    81  -3.2  -6.6
##  8 CentralPark_NY USW00094728 2017-01-08     0  -3.8  -8.8
##  9 CentralPark_NY USW00094728 2017-01-09     0  -4.9  -9.9
## 10 CentralPark_NY USW00094728 2017-01-10     0   7.8  -6  
## # ... with 1,085 more rows

Start a plot

First scatterplot, but fancier!

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) +
  labs(
    title = "Temperature plot",
    x = "Minimum daily temperature (C)",
    y = "Maxiumum daily temperature (C)",
    caption = "Data from the rnoaa package"
  )
## Warning: Removed 15 rows containing missing values (geom_point).

Tick marks and labels…

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) +
  labs(
    title = "Temperature plot",
    x = "Minimum daily temperature (C)",
    y = "Maxiumum daily temperature (C)",
    caption = "Data from the rnoaa package"
  ) +
  scale_x_continuous(
    breaks = c(-15, 0, 15),
    labels = c("-15 ºC", "0 ºC", "15 ºC")
  )
## Warning: Removed 15 rows containing missing values (geom_point).

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) +
  labs(
    title = "Temperature plot",
    x = "Minimum daily temperature (C)",
    y = "Maxiumum daily temperature (C)",
    caption = "Data from the rnoaa package"
  ) +
  scale_x_continuous(
    breaks = c(-15, 0, 15),
    labels = c("-15 ºC", "0 ºC", "15 ºC"),
    limits = c(-20, 42)
  ) +
  scale_y_continuous(
    position = "right",
    trans = "sqrt"
  )
## Warning in self$trans$transform(x): NaNs produced
## Warning: Transformation introduced infinite values in continuous y-axis
## Warning: Removed 90 rows containing missing values (geom_point).

Colors

Adjust color

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) +
  labs(
    title = "Temperature plot",
    x = "Minimum daily temperature (C)",
    y = "Maxiumum daily temperature (C)",
    caption = "Data from the rnoaa package"
  ) +
  scale_color_hue(
    name = "Location",
    h = c(100, 350), 
    l = 75
  )
## Warning: Removed 15 rows containing missing values (geom_point).

Viridis package and legend formatting

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) +
  labs(
    title = "Temperature plot",
    x = "Minimum daily temperature (C)",
    y = "Maxiumum daily temperature (C)",
    caption = "Data from the rnoaa package"
  ) +
  viridis::scale_color_viridis(
    name = "Location",
    discrete = TRUE
  ) +
  theme(legend.position = "bottom")
## Warning: Removed 15 rows containing missing values (geom_point).

Themes

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) +
  labs(
    title = "Temperature plot",
    x = "Minimum daily temperature (C)",
    y = "Maxiumum daily temperature (C)",
    caption = "Data from the rnoaa package"
  ) +
  viridis::scale_color_viridis(
    name = "Location",
    discrete = TRUE
  ) +
  theme_bw() +
  theme(legend.position = "bottom")
## Warning: Removed 15 rows containing missing values (geom_point).

Learning Assessment:

ggplot(weather_df, aes(x = date, y = tmax, color = name)) +
  geom_point(aes(size = prcp), alpha = 0.75) +
  geom_smooth(se = FALSE) +
   labs(
    title = "2017 Maximum Temperature Plot",
    x = "Date",
    y = "Maxiumum daily temperature (ºC)",
    caption = "Data from the rnoaa package"
  ) +
    viridis::scale_color_viridis(
    name = "Location",
    discrete = TRUE
  ) +
  theme_minimal() +
  theme(legend.position = "bottom")
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).
## Warning: Removed 3 rows containing missing values (geom_point).

Arguments to geom_*

centralpark_df = weather_df %>% filter(name == "CentralPark_NY")
waikiki_df = weather_df %>% filter(name == "Waikiki_HA")

ggplot(waikiki_df, aes(x = date, y = tmax, color = name)) +
  geom_point() +
  geom_line(data = centralpark_df)
## Warning: Removed 3 rows containing missing values (geom_point).

patchwork

Where patchwork is not needed:

ggplot(weather_df, aes(x = date, y = tmax, color = name)) +
  geom_point(aes(size = prcp), alpha = 0.75) +
  geom_smooth(se = FALSE) +
  facet_grid(~name) +
   labs(
    title = "2017 Maximum Temperature Plot",
    x = "Date",
    y = "Maxiumum daily temperature (ºC)",
    caption = "Data from the rnoaa package"
  ) +
    viridis::scale_color_viridis(
    name = "Location",
    discrete = TRUE
  ) +
  theme_minimal() +
  theme(legend.position = "bottom")
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).
## Warning: Removed 3 rows containing missing values (geom_point).

patchwork install:

devtools::install_github("thomasp85/patchwork")
## Skipping install of 'patchwork' from a github remote, the SHA1 (fd7958ba) has not changed since last install.
##   Use `force = TRUE` to force installation
library(patchwork)

Where patchwork is needed:

tmax_tmin_p = ggplot(weather_df, aes(x = tmax, y = tmin, color = name)) + 
  geom_point(alpha = .5) +
  theme(legend.position = "none")

prcp_dens_p = weather_df %>% 
  filter(prcp > 0) %>% 
  ggplot(aes(x = prcp, fill = name)) + 
  geom_density(alpha = .5) + 
  theme(legend.position = "none")

tmax_date_p = ggplot(weather_df, aes(x = date, y = tmax, color = name)) + 
  geom_point(alpha = .5) +
  geom_smooth(se = FALSE) + 
  theme(legend.position = "bottom")

tmax_tmin_p + prcp_dens_p
## Warning: Removed 15 rows containing missing values (geom_point).

(tmax_tmin_p + prcp_dens_p) / tmax_date_p
## Warning: Removed 15 rows containing missing values (geom_point).
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).
## Warning: Removed 3 rows containing missing values (geom_point).

Data manipulation

factors….

ggplot(weather_df, aes(x = name, y = tmax, fill = name)) +
  geom_violin()
## Warning: Removed 3 rows containing non-finite values (stat_ydensity).

weather_df %>%
  mutate(name = forcats::fct_relevel(name, c("Waikiki_HA", "CentralPark_NY", "Waterhole_WA"))) %>% 
  ggplot(aes(x = name, y = tmax)) + 
  geom_violin(aes(fill = name), color = "blue", alpha = .5) + 
  theme(legend.position = "bottom")
## Warning: Removed 3 rows containing non-finite values (stat_ydensity).

weather_df %>%
  mutate(name = forcats::fct_reorder(name, tmax)) %>% 
  ggplot(aes(x = name, y = tmax)) + 
  geom_violin(aes(fill = name), color = "blue", alpha = .5) + 
  theme(legend.position = "bottom")
## Warning: Removed 3 rows containing non-finite values (stat_ydensity).

Advanced tidying:

weather_df %>%
  select(name, tmax, tmin) %>% 
  gather(key = observation, value = temp, tmax:tmin) %>% 
  ggplot(aes(x = temp, fill = observation)) +
  geom_density(alpha = .5) + 
  facet_grid(~name) + 
  viridis::scale_fill_viridis(discrete = TRUE)
## Warning: Removed 18 rows containing non-finite values (stat_density).